#include <asm/desc.h>
#include <asm/mtrr.h>
#include <asm/mce.h>
+#include <asm/i387.h>
+#include <asm/xcr.h>
#define MAX_IO_MSRS 256
#define CR0_RESERVED_BITS \
static int __kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
+ unsigned long old_cr0 = kvm_read_cr0(vcpu);
+ unsigned long update_bits = X86_CR0_PG | X86_CR0_WP |
+ X86_CR0_CD | X86_CR0_NW;
+
cr0 |= X86_CR0_ET;
#ifdef CONFIG_X86_64
kvm_x86_ops->set_cr0(vcpu, cr0);
- kvm_mmu_reset_context(vcpu);
+ if ((cr0 ^ old_cr0) & update_bits)
+ kvm_mmu_reset_context(vcpu);
return 0;
}
return 1;
kvm_x86_ops->set_cr4(vcpu, cr4);
- vcpu->arch.cr4 = cr4;
- kvm_mmu_reset_context(vcpu);
+
+ if ((cr4 ^ old_cr4) & pdptr_bits)
+ kvm_mmu_reset_context(vcpu);
return 0;
}
static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
+ u64 old_efer = vcpu->arch.efer;
+
if (efer & efer_reserved_bits)
return 1;
kvm_x86_ops->set_efer(vcpu, efer);
- vcpu->arch.efer = efer;
-
vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
kvm_mmu_reset_context(vcpu);
+ /* Update reserved bits */
+ if ((efer ^ old_efer) & EFER_NX)
+ kvm_mmu_reset_context(vcpu);
+
return 0;
}
{
int i, idx;
- vcpu_load(vcpu);
-
idx = srcu_read_lock(&vcpu->kvm->srcu);
for (i = 0; i < msrs->nmsrs; ++i)
if (do_msr(vcpu, entries[i].index, &entries[i].data))
break;
srcu_read_unlock(&vcpu->kvm->srcu, idx);
- vcpu_put(vcpu);
-
return i;
}
if (copy_from_user(cpuid_entries, entries,
cpuid->nent * sizeof(struct kvm_cpuid_entry)))
goto out_free;
- vcpu_load(vcpu);
for (i = 0; i < cpuid->nent; i++) {
vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
r = 0;
kvm_apic_set_version(vcpu);
kvm_x86_ops->cpuid_update(vcpu);
- vcpu_put(vcpu);
out_free:
vfree(cpuid_entries);
if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
goto out;
- vcpu_load(vcpu);
vcpu->arch.cpuid_nent = cpuid->nent;
kvm_apic_set_version(vcpu);
kvm_x86_ops->cpuid_update(vcpu);
- vcpu_put(vcpu);
return 0;
out:
{
int r;
- vcpu_load(vcpu);
r = -E2BIG;
if (cpuid->nent < vcpu->arch.cpuid_nent)
goto out;
out:
cpuid->nent = vcpu->arch.cpuid_nent;
- vcpu_put(vcpu);
return r;
}
static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s)
{
- vcpu_load(vcpu);
memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s);
- vcpu_put(vcpu);
return 0;
}
static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s)
{
- vcpu_load(vcpu);
memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
kvm_apic_post_state_restore(vcpu);
update_cr8_intercept(vcpu);
- vcpu_put(vcpu);
return 0;
}
return -EINVAL;
if (irqchip_in_kernel(vcpu->kvm))
return -ENXIO;
- vcpu_load(vcpu);
kvm_queue_interrupt(vcpu, irq->irq, false);
- vcpu_put(vcpu);
-
return 0;
}
static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
{
- vcpu_load(vcpu);
kvm_inject_nmi(vcpu);
- vcpu_put(vcpu);
return 0;
}
int r;
unsigned bank_num = mcg_cap & 0xff, bank;
- vcpu_load(vcpu);
r = -EINVAL;
if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
goto out;
for (bank = 0; bank < bank_num; bank++)
vcpu->arch.mce_banks[bank*4] = ~(u64)0;
out:
- vcpu_put(vcpu);
return r;
}
static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
- vcpu_load(vcpu);
-
events->exception.injected =
vcpu->arch.exception.pending &&
!kvm_exception_is_soft(vcpu->arch.exception.nr);
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
| KVM_VCPUEVENT_VALID_SIPI_VECTOR
| KVM_VCPUEVENT_VALID_SHADOW);
-
- vcpu_put(vcpu);
}
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
| KVM_VCPUEVENT_VALID_SHADOW))
return -EINVAL;
- vcpu_load(vcpu);
-
vcpu->arch.exception.pending = events->exception.injected;
vcpu->arch.exception.nr = events->exception.nr;
vcpu->arch.exception.has_error_code = events->exception.has_error_code;
if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR)
vcpu->arch.sipi_vector = events->sipi_vector;
- vcpu_put(vcpu);
-
return 0;
}
static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
struct kvm_debugregs *dbgregs)
{
- vcpu_load(vcpu);
-
memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
dbgregs->dr6 = vcpu->arch.dr6;
dbgregs->dr7 = vcpu->arch.dr7;
dbgregs->flags = 0;
-
- vcpu_put(vcpu);
}
static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
if (dbgregs->flags)
return -EINVAL;
- vcpu_load(vcpu);
-
memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
vcpu->arch.dr6 = dbgregs->dr6;
vcpu->arch.dr7 = dbgregs->dr7;
- vcpu_put(vcpu);
-
return 0;
}
r = -EFAULT;
if (copy_from_user(&mce, argp, sizeof mce))
goto out;
- vcpu_load(vcpu);
r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce);
- vcpu_put(vcpu);
break;
}
case KVM_GET_VCPU_EVENTS: {
return __kvm_set_dr(vcpu, dr, value);
}
-void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
-{
- u8 opcodes[4];
- unsigned long rip = kvm_rip_read(vcpu);
- unsigned long rip_linear;
-
- if (!printk_ratelimit())
- return;
-
- rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS);
-
- kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu, NULL);
-
- printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n",
- context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]);
-}
-EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
-
static u64 mk_cr_64(u64 curr_cr, u32 new_val)
{
return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
vcpu->arch.regs_dirty = ~0;
}
+static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
+{
+ u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(vcpu, mask);
+ /*
+ * an sti; sti; sequence only disable interrupts for the first
+ * instruction. So, if the last instruction, be it emulated or
+ * not, left the system with the INT_STI flag enabled, it
+ * means that the last instruction is an sti. We should not
+ * leave the flag on in this case. The same goes for mov ss
+ */
+ if (!(int_shadow & mask))
+ kvm_x86_ops->set_interrupt_shadow(vcpu, mask);
+}
+
+static void inject_emulated_exception(struct kvm_vcpu *vcpu)
+{
+ struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
+ if (ctxt->exception == PF_VECTOR)
+ kvm_inject_page_fault(vcpu, ctxt->cr2, ctxt->error_code);
+ else if (ctxt->error_code_valid)
+ kvm_queue_exception_e(vcpu, ctxt->exception, ctxt->error_code);
+ else
+ kvm_queue_exception(vcpu, ctxt->exception);
+}
+
+static int handle_emulation_failure(struct kvm_vcpu *vcpu)
+{
+ ++vcpu->stat.insn_emulation_fail;
+ trace_kvm_emulate_insn_failed(vcpu);
+ vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ vcpu->run->internal.ndata = 0;
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return EMULATE_FAIL;
+}
+
int emulate_instruction(struct kvm_vcpu *vcpu,
unsigned long cr2,
u16 error_code,
int emulation_type)
{
- int r, shadow_mask;
+ int r;
struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode;
kvm_clear_exception_queue(vcpu);
? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
memset(c, 0, sizeof(struct decode_cache));
memcpy(c->regs, vcpu->arch.regs, sizeof c->regs);
+ vcpu->arch.emulate_ctxt.interruptibility = 0;
+ vcpu->arch.emulate_ctxt.exception = -1;
r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
trace_kvm_emulate_insn_start(vcpu);
++vcpu->stat.insn_emulation;
if (r) {
- ++vcpu->stat.insn_emulation_fail;
- trace_kvm_emulate_insn_failed(vcpu);
if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
return EMULATE_DONE;
- return EMULATE_FAIL;
+ if (emulation_type & EMULTYPE_SKIP)
+ return EMULATE_FAIL;
+ return handle_emulation_failure(vcpu);
}
}
if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
return EMULATE_DONE;
- trace_kvm_emulate_insn_failed(vcpu);
- kvm_report_emulation_failure(vcpu, "mmio");
- return EMULATE_FAIL;
+ return handle_emulation_failure(vcpu);
}
- shadow_mask = vcpu->arch.emulate_ctxt.interruptibility;
- kvm_x86_ops->set_interrupt_shadow(vcpu, shadow_mask);
+ toggle_interruptibility(vcpu, vcpu->arch.emulate_ctxt.interruptibility);
kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
memcpy(vcpu->arch.regs, c->regs, sizeof c->regs);
kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip);
+ if (vcpu->arch.emulate_ctxt.exception >= 0) {
+ inject_emulated_exception(vcpu);
+ return EMULATE_DONE;
+ }
+
if (vcpu->arch.pio.count) {
if (!vcpu->arch.pio.in)
vcpu->arch.pio.count = 0;
return EMULATE_DO_MMIO;
}
- if (vcpu->arch.exception.pending)
- vcpu->arch.emulate_ctxt.restart = false;
-
if (vcpu->arch.emulate_ctxt.restart)
goto restart;
if (vcpu->fpu_active)
kvm_load_guest_fpu(vcpu);
- local_irq_disable();
+ atomic_set(&vcpu->guest_mode, 1);
+ smp_wmb();
- clear_bit(KVM_REQ_KICK, &vcpu->requests);
- smp_mb__after_clear_bit();
+ local_irq_disable();
- if (vcpu->requests || need_resched() || signal_pending(current)) {
- set_bit(KVM_REQ_KICK, &vcpu->requests);
+ if (!atomic_read(&vcpu->guest_mode) || vcpu->requests
+ || need_resched() || signal_pending(current)) {
+ atomic_set(&vcpu->guest_mode, 0);
+ smp_wmb();
local_irq_enable();
preempt_enable();
r = 1;
if (hw_breakpoint_active())
hw_breakpoint_restore();
- set_bit(KVM_REQ_KICK, &vcpu->requests);
+ atomic_set(&vcpu->guest_mode, 0);
+ smp_wmb();
local_irq_enable();
++vcpu->stat.exits;
int r;
sigset_t sigsaved;
- vcpu_load(vcpu);
-
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
- if (r == EMULATE_DO_MMIO) {
+ if (r != EMULATE_DONE) {
r = 0;
goto out;
}
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
- vcpu_put(vcpu);
return r;
}
int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
- vcpu_load(vcpu);
-
regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX);
regs->rbx = kvm_register_read(vcpu, VCPU_REGS_RBX);
regs->rcx = kvm_register_read(vcpu, VCPU_REGS_RCX);
regs->rip = kvm_rip_read(vcpu);
regs->rflags = kvm_get_rflags(vcpu);
- vcpu_put(vcpu);
-
return 0;
}
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
- vcpu_load(vcpu);
-
kvm_register_write(vcpu, VCPU_REGS_RAX, regs->rax);
kvm_register_write(vcpu, VCPU_REGS_RBX, regs->rbx);
kvm_register_write(vcpu, VCPU_REGS_RCX, regs->rcx);
vcpu->arch.exception.pending = false;
- vcpu_put(vcpu);
-
return 0;
}
{
struct desc_ptr dt;
- vcpu_load(vcpu);
-
kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES);
set_bit(vcpu->arch.interrupt.nr,
(unsigned long *)sregs->interrupt_bitmap);
- vcpu_put(vcpu);
-
return 0;
}
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
- vcpu_load(vcpu);
mp_state->mp_state = vcpu->arch.mp_state;
- vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
- vcpu_load(vcpu);
vcpu->arch.mp_state = mp_state->mp_state;
- vcpu_put(vcpu);
return 0;
}
int pending_vec, max_bits;
struct desc_ptr dt;
- vcpu_load(vcpu);
-
dt.size = sregs->idt.limit;
dt.address = sregs->idt.base;
kvm_x86_ops->set_idt(vcpu, &dt);
!is_protmode(vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
- vcpu_put(vcpu);
-
return 0;
}
unsigned long rflags;
int i, r;
- vcpu_load(vcpu);
-
if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) {
r = -EBUSY;
if (vcpu->arch.exception.pending)
- goto unlock_out;
+ goto out;
if (dbg->control & KVM_GUESTDBG_INJECT_DB)
kvm_queue_exception(vcpu, DB_VECTOR);
else
r = 0;
-unlock_out:
- vcpu_put(vcpu);
+out:
return r;
}
-/*
- * fxsave fpu state. Taken from x86_64/processor.h. To be killed when
- * we have asm/x86/processor.h
- */
-struct fxsave {
- u16 cwd;
- u16 swd;
- u16 twd;
- u16 fop;
- u64 rip;
- u64 rdp;
- u32 mxcsr;
- u32 mxcsr_mask;
- u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
-#ifdef CONFIG_X86_64
- u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 256 bytes */
-#else
- u32 xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */
-#endif
-};
-
/*
* Translate a guest virtual address to a guest physical address.
*/
gpa_t gpa;
int idx;
- vcpu_load(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
tr->valid = gpa != UNMAPPED_GVA;
tr->writeable = 1;
tr->usermode = 0;
- vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct fxsave *fxsave = (struct fxsave *)&vcpu->arch.guest_fx_image;
-
- vcpu_load(vcpu);
+ struct i387_fxsave_struct *fxsave =
+ &vcpu->arch.guest_fpu.state->fxsave;
memcpy(fpu->fpr, fxsave->st_space, 128);
fpu->fcw = fxsave->cwd;
fpu->last_dp = fxsave->rdp;
memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space);
- vcpu_put(vcpu);
-
return 0;
}
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct fxsave *fxsave = (struct fxsave *)&vcpu->arch.guest_fx_image;
-
- vcpu_load(vcpu);
+ struct i387_fxsave_struct *fxsave =
+ &vcpu->arch.guest_fpu.state->fxsave;
memcpy(fxsave->st_space, fpu->fpr, 128);
fxsave->cwd = fpu->fcw;
fxsave->rdp = fpu->last_dp;
memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space);
- vcpu_put(vcpu);
-
return 0;
}
void fx_init(struct kvm_vcpu *vcpu)
{
- unsigned after_mxcsr_mask;
-
- /*
- * Touch the fpu the first time in non atomic context as if
- * this is the first fpu instruction the exception handler
- * will fire before the instruction returns and it'll have to
- * allocate ram with GFP_KERNEL.
- */
- if (!used_math())
- kvm_fx_save(&vcpu->arch.host_fx_image);
-
- /* Initialize guest FPU by resetting ours and saving into guest's */
- preempt_disable();
- kvm_fx_save(&vcpu->arch.host_fx_image);
- kvm_fx_finit();
- kvm_fx_save(&vcpu->arch.guest_fx_image);
- kvm_fx_restore(&vcpu->arch.host_fx_image);
- preempt_enable();
+ fpu_alloc(&vcpu->arch.guest_fpu);
+ fpu_finit(&vcpu->arch.guest_fpu);
vcpu->arch.cr0 |= X86_CR0_ET;
- after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space);
- vcpu->arch.guest_fx_image.mxcsr = 0x1f80;
- memset((void *)&vcpu->arch.guest_fx_image + after_mxcsr_mask,
- 0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask);
}
EXPORT_SYMBOL_GPL(fx_init);
+static void fx_free(struct kvm_vcpu *vcpu)
+{
+ fpu_free(&vcpu->arch.guest_fpu);
+}
+
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
{
if (vcpu->guest_fpu_loaded)
return;
vcpu->guest_fpu_loaded = 1;
- kvm_fx_save(&vcpu->arch.host_fx_image);
- kvm_fx_restore(&vcpu->arch.guest_fx_image);
+ unlazy_fpu(current);
+ fpu_restore_checking(&vcpu->arch.guest_fpu);
trace_kvm_fpu(1);
}
return;
vcpu->guest_fpu_loaded = 0;
- kvm_fx_save(&vcpu->arch.guest_fx_image);
- kvm_fx_restore(&vcpu->arch.host_fx_image);
+ fpu_save_init(&vcpu->arch.guest_fpu);
++vcpu->stat.fpu_reload;
set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests);
trace_kvm_fpu(0);
vcpu->arch.time_page = NULL;
}
+ fx_free(vcpu);
kvm_x86_ops->vcpu_free(vcpu);
}
{
int r;
- /* We do fxsave: this must be aligned. */
- BUG_ON((unsigned long)&vcpu->arch.host_fx_image & 0xF);
-
vcpu->arch.mtrr_state.have_fixed = 1;
vcpu_load(vcpu);
r = kvm_arch_vcpu_reset(vcpu);
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
+ fx_free(vcpu);
kvm_x86_ops->vcpu_free(vcpu);
}
me = get_cpu();
if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
- if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests))
+ if (atomic_xchg(&vcpu->guest_mode, 0))
smp_send_reschedule(cpu);
put_cpu();
}
git.openpandora.org / pandora-kernel.git / blobdiff